R Notebook

Import Dataset and create working dataset:

#install.packages("plotly")
library(plotly)

package 㤼㸱plotly㤼㸲 was built under R version 4.0.4Loading required package: ggplot2
Learn more about the underlying theory at https://ggplot2-book.org/
Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: 㤼㸱plotly㤼㸲

The following object is masked from 㤼㸱package:ggplot2㤼㸲:

    last_plot

The following object is masked from 㤼㸱package:stats㤼㸲:

    filter

The following object is masked from 㤼㸱package:graphics㤼㸲:

    layout

library(reshape2)

package 㤼㸱reshape2㤼㸲 was built under R version 4.0.3

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
-- Attaching packages --------------------------------------------------------------------------------------------------------------------------------------------- tidyverse 1.3.0 --
v tibble  3.0.3     v dplyr   1.0.2
v tidyr   1.1.2     v stringr 1.4.0
v readr   1.3.1     v forcats 0.5.0
v purrr   0.3.4     
-- Conflicts ------------------------------------------------------------------------------------------------------------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks plotly::filter(), stats::filter()
x dplyr::lag()    masks stats::lag()

games <- read.csv("../../data/vgsales.csv")
game_melt <- melt(data=games,id.vars = c("Rank","Name","Platform","Year","Genre","Publisher"),measure.vars=c("NA_Sales","EU_Sales","JP_Sales","Other_Sales","Global_Sales"))
game_melt$Year <- as.integer(game_melt$Year)

NAs introduced by coercion

colnames(game_melt)[7] <- "Region"
colnames(game_melt)[8] <- "Copies Sold"
head(game_melt)

Graph time baby!

#Number of Copies Sold
graph1 <- game_melt %>% 
    filter(Region == "NA_Sales") %>%
    group_by(Region,Year,Genre) %>%
    summarise("Copies Sold" = sum(`Copies Sold`)) %>% 
    ggplot() +
    aes(x=Year,
        y=`Copies Sold`,
        fill = Genre) + 
    geom_bar(stat="identity")+
    theme(axis.text.x = element_text(angle = 90, hjust=0.95, vjust=0.2)) +
    ylab("Number of Copies Sold (in millions)")

`summarise()` regrouping output by 'Region', 'Year' (override with `.groups` argument)

    
ggplotly(graph1)

Removed 12 rows containing missing values (position_stack).

#Number Releases
graph2 <- game_melt %>% 
    filter(Region == "NA_Sales") %>%
    group_by(Region,Year,Genre) %>%
    count(Genre) %>%
    rename(`Number of Releases`="n")%>% 
    ggplot() +
    aes(x=Year,
        y=`Number of Releases`,
        fill = Genre) + 
    geom_bar(stat="identity")+
    theme(axis.text.x = element_text(angle = 90, hjust=0.95, vjust=0.2))+
    ylab("Number of Games Released")
ggplotly(graph2)

Removed 12 rows containing missing values (position_stack).

is.list(y)

[1] TRUE

testfxc1 <-function(reg,plat,gen,pub,years) {
         # Input: List of Regions, Platforms, Genres, Publishers, Min and Max Year
         # Output: Graph
         #
         # Create subset based on filters 
         # Pass to graph
         # Output graph
        if ("Global_Sales" %in% reg){
            filter_region = list("Global_Sales")
        } else {
            filter_region = reg
        }
         if ("all" %in% plat){
             filter_plat = unique(game_melt$Platform)
         } else {
             filter_plat = plat
         }
         if ("all" %in% gen){
             filter_gen = unique(game_melt$Genre)
         } else {
             filter_gen = gen
         }
         if ("all" %in% pub){
             filter_pub = unique(game_melt$Publisher)
         } else {
             filter_pub = pub
         }
         min_year = years[1]
         max_year = years[2]
         
         graph1 <- game_melt[,3:8] %>% 
             subset(Region %in% filter_region & Platform %in% filter_plat & Genre %in% filter_gen & Publisher %in% filter_pub & Year >= min_year & Year <= max_year) %>%
             group_by(Year,Genre) %>%
             summarise("Copies Sold" = sum(`Copies Sold`)) %>% 
             ggplot() +
             aes(x=as.factor(Year),
                 y=`Copies Sold`,
                 fill = Genre) + 
             geom_bar(stat="identity")+
             theme(axis.text.x = element_text(angle = 90, hjust=0.95, vjust=0.2)) +
             ylab("Total Game Copies Sold (in millions)")
         
         return (ggplotly(graph1))
}

testfxc2 <-function(reg,plat,gen,pub,years) {
        # Input: List of Regions, Platforms, Genres, Publishers, Min and Max Year
        # Output: Graph
        #
        # Create subset based on filters 
        # Pass to graph
        # Output graph
        if ("Global_Sales" %in% reg){
            filter_region = list("Global_Sales")
        } else {
            filter_region = reg
        }
        if ("all" %in% plat){
            filter_plat = unique(game_melt$Platform)
        } else {
            filter_plat = plat
        }
        if ("all" %in% gen){
            filter_gen = unique(game_melt$Genre)
        } else {
            filter_gen = gen
        }
        if ("all" %in% pub){
            filter_pub = unique(game_melt$Publisher)
        } else {
            filter_pub = pub
        }
        min_year = years[1]
        max_year = years[2]
        
        graph2 <- game_melt[,3:8] %>% 
            subset(Region %in% filter_region & Platform %in% filter_plat & Genre %in% filter_gen & Publisher %in% filter_pub & Year >= min_year & Year <= max_year) %>%
            group_by(Year,Genre) %>%
            count(Year,Genre) %>%
            rename(`Number of Releases`="n") %>% 
            ggplot() +
            aes(x=as.factor(Year),
                y=`Number of Releases`,
                fill = Genre) + 
            geom_bar(stat="identity")+
            theme(axis.text.x = element_text(angle = 90, hjust=0.95, vjust=0.2))+
            ylab("Number of Games Released")

        return (ggplotly(graph2))
    }

filter_region = list("JP_Sales")
filter_plat = list("N64")
filter_gen = unique(game_melt$Genre)
filter_pub = unique(game_melt$Publisher)
min_year = 1980
max_year = 1990
test <- game_melt %>% 
    subset(Region %in% filter_region & Platform %in% filter_plat & Genre %in% filter_gen & Publisher %in% filter_pub & Year >= min_year & Year <= max_year)
dim(test)

[1] 0 8